Mohammad Ashraf Bhuiyan
Senior Software Engineering Manager at Red Hat AI , IBM | Scaling AI Inference with vLLM Runtime[Ex Intel leader for Scaling JAX, TensorFlow, and OpenXLA]
- Role
- Senior Software Engineering Manager, Red Hat Ai at Red Hat
- Location
- Hillsboro, OR, US
- LinkedIn followers
- 500 followers
About Mohammad Ashraf Bhuiyan
I am a Senior Software Engineering Manager specializing in software optimizations towards high-performance and scaling with over 18 years of experience. I am currently applying this expertise to accelerate and scale on multi-GPU and multi-node vLLM inference at Red Hat AI, IBM. leading a highly talented team. Previously, I spent over six years as an Engineering Manager at Intel Corporation, leading talented teams of engineers responsible for accelerate and scale key AI frameworks: TensorFlow, JAX, and OpenXLA. A major achievement was establishing Intel\'s optimization as the default for Google\'s TensorFlow (starting with TF 2.9). My deep technical foundation, supported by a Ph.D, includes extensive work in HPC (optimizing and scaling molecular dynamics, weather simulations) and technical contributions that led to two issued patents.Key Skills:Strong Programming skills – expertise in C/C++ and Python, Parallel programming in CUDA, OpenCL, POSIX-threading, OpenMP, MPI, NCCL, CUDA librariesApplication acceleration using Intel/AMD Multi-Core CPU, NVIDIA/AMD GPU, and FPGA-based systemsTools: Visual studio, Intel VTune, NVIDIA Nsys/NCUScaling AI training/inference and HPC on various Supercomputers: vLLM inference, TensorFLow/JAX, OpenXLA, scientific algorithms
Experience
Senior Software Engineering Manager, Red Hat Ai
Oct 2025 — Present
Managing vLLM runtime engine.
Education
Bangladesh University of Engineering and Technology
Masters of Science, Computer Science and Engineering
2002 — 2005
Clemson University
Ph. D., Computer Engineering
2008 — 2011
Bangladesh University of Engineering and Technology
Bachelor of Science, Electrical and Electronics Engineering
1994 — 1999
Skills
- Algorithms
- C++
- Parallel Computing
- Parallel Programming
- Software Engineering
- Low Level Programming
- Mpi
- Openmp
- Gpu
- Linux
- Multi-Core
- Gpgpu
- C/C++ Stl
- C
- Programming
- Optimization
- Vhdl
- Simulations
- High Performance Computing
- Opencl
- Cuda
- Fpga
- Matlab
Find verified contacts for anyone on LinkedIn
Unifers gives sales teams verified emails and direct dials, enriched profiles, and outreach that lands in the inbox.
Free plan included · No credit card required
This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.